Content-based image retrieval, also known as query by image content is the application of computer vision techniques to the image retrieval problem, that is, the problem of searching for digital images in large databases. The design & development of image authentication algorithm based on quartic digital signature for a competent content based image retrieval system using block division with eigen features and supervised labeling is presented. Algorithms are developed using the mathematical models & the simulations are carried out in the Python environment to show the retrieving efficiency from the databases.